AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	auc	0.5	0.96
	2_DecisionTree	Decision Tree	auc	0.503766	7.1
	3_Linear	Linear	auc	0.523886	2.66
	4_Default_Xgboost	Xgboost	auc	0.504215	57.43
	5_Default_NeuralNetwork	Neural Network	auc	0.495056	2.48
	6_Default_RandomForest	Random Forest	auc	0.554559	6.29
the best	Ensemble	Ensemble	auc	0.559287	0.48

AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 5_Default_NeuralNetwork

<< Go back

Neural Network

• n_jobs: -1
• dense_1_size: 32
• dense_2_size: 16
• learning_rate: 0.05
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

1.6 seconds

Metric details

	score	threshold
logloss	1.28771	nan
auc	0.495056	nan
f1	0.648649	1.02425e-22
accuracy	0.536	0.798809
precision	0.557143	0.798809
recall	1	1.02425e-22
mcc	0.0623	0.798809

Metric details with threshold from accuracy metric

	score	threshold
logloss	1.28771	nan
auc	0.495056	nan
f1	0.251613	0.798809
accuracy	0.536	0.798809
precision	0.557143	0.798809
recall	0.1625	0.798809
mcc	0.0623	0.798809

Confusion matrix (at threshold=0.798809)

	Predicted as 0	Predicted as 1
Labeled as 0	229	31
Labeled as 1	201	39

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

0.3 seconds

Metric details

	score	threshold
logloss	0.692348	nan
auc	0.5	nan
f1	0.648649	0.4314
accuracy	0.48	0.4314
precision	0.48	0.4314
recall	1	0.4314
mcc	0	0.4314

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.692348	nan
auc	0.5	nan
f1	0.648649	0.4314
accuracy	0.48	0.4314
precision	0.48	0.4314
recall	1	0.4314
mcc	0	0.4314

Confusion matrix (at threshold=0.4314)

	Predicted as 0	Predicted as 1
Labeled as 0	0	260
Labeled as 1	0	240

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
2_DecisionTree	1
4_Default_Xgboost	1
6_Default_RandomForest	2

Metric details

	score	threshold
logloss	0.693207	nan
auc	0.559287	nan
f1	0.648649	0.247797
accuracy	0.572	0.491957
precision	0.571429	0.491957
recall	1	0.247797
mcc	0.138482	0.490173

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.693207	nan
auc	0.559287	nan
f1	0.492891	0.491957
accuracy	0.572	0.491957
precision	0.571429	0.491957
recall	0.433333	0.491957
mcc	0.138446	0.491957

Confusion matrix (at threshold=0.491957)

	Predicted as 0	Predicted as 1
Labeled as 0	182	78
Labeled as 1	136	104

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

• n_jobs: -1
• criterion: gini
• max_depth: 3
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

6.1 seconds

Metric details

	score	threshold
logloss	0.717369	nan
auc	0.503766	nan
f1	0.648649	0.072
accuracy	0.522	0.465873
precision	0.506849	0.465873
recall	1	0.072
mcc	0.0222207	0.465873

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.717369	nan
auc	0.503766	nan
f1	0.236422	0.465873
accuracy	0.522	0.465873
precision	0.506849	0.465873
recall	0.154167	0.465873
mcc	0.0222207	0.465873

Confusion matrix (at threshold=0.465873)

	Predicted as 0	Predicted as 1
Labeled as 0	224	36
Labeled as 1	203	37

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 6_Default_RandomForest

<< Go back

Random Forest

• n_jobs: -1
• criterion: gini
• max_features: 0.9
• min_samples_split: 30
• max_depth: 4
• eval_metric_name: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

5.3 seconds

Metric details

	score	threshold
logloss	0.692599	nan
auc	0.554559	nan
f1	0.648649	0.246802
accuracy	0.564	0.49588
precision	0.562874	0.499565
recall	1	0.246802
mcc	0.121917	0.49588

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.692599	nan
auc	0.554559	nan
f1	0.488263	0.49588
accuracy	0.564	0.49588
precision	0.55914	0.49588
recall	0.433333	0.49588
mcc	0.121917	0.49588

Confusion matrix (at threshold=0.49588)

	Predicted as 0	Predicted as 1
Labeled as 0	178	82
Labeled as 1	136	104

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 4_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: -1
• objective: binary:logistic
• eta: 0.075
• max_depth: 6
• min_child_weight: 1
• subsample: 1.0
• colsample_bytree: 1.0
• eval_metric: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

56.4 seconds

Metric details

	score	threshold
logloss	0.693393	nan
auc	0.504215	nan
f1	0.648649	0.424219
accuracy	0.522	0.496033
precision	0.502203	0.496033
recall	1	0.424219
mcc	0.0405242	0.496033

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.693393	nan
auc	0.504215	nan
f1	0.488223	0.496033
accuracy	0.522	0.496033
precision	0.502203	0.496033
recall	0.475	0.496033
mcc	0.0405242	0.496033

Confusion matrix (at threshold=0.496033)

	Predicted as 0	Predicted as 1
Labeled as 0	147	113
Labeled as 1	126	114

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 3_Linear

<< Go back

Logistic Regression (Linear)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

1.6 seconds

Metric details

	score	threshold
logloss	0.712674	nan
auc	0.523886	nan
f1	0.648649	0.132938
accuracy	0.55	0.532795
precision	0.557252	0.532795
recall	1	0.132938
mcc	0.0921318	0.532795

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.712674	nan
auc	0.523886	nan
f1	0.393531	0.532795
accuracy	0.55	0.532795
precision	0.557252	0.532795
recall	0.304167	0.532795
mcc	0.0921318	0.532795

Confusion matrix (at threshold=0.532795)

	Predicted as 0	Predicted as 1
Labeled as 0	202	58
Labeled as 1	167	73

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back